scholarly journals Attitudes towards Trusting Artificial Intelligence Insights and Factors to Prevent the Passive Adherence of GPs: A Pilot Study

2021 ◽  
Vol 10 (14) ◽  
pp. 3101
Author(s):  
Massimo Micocci ◽  
Simone Borsci ◽  
Viral Thakerar ◽  
Simon Walne ◽  
Yasmine Manshadi ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Domain Knowledge ◽  
Online Survey ◽  
Decision Support Tool ◽  
Skin Lesions ◽  
Management Plan ◽  
Individual Characteristics ◽  
System Efficiency ◽  
Support Tool ◽  
The Difference

Artificial Intelligence (AI) systems could improve system efficiency by supporting clinicians in making appropriate referrals. However, they are imperfect by nature and misdiagnoses, if not correctly identified, can have consequences for patient care. In this paper, findings from an online survey are presented to understand the aptitude of GPs (n = 50) in appropriately trusting or not trusting the output of a fictitious AI-based decision support tool when assessing skin lesions, and to identify which individual characteristics could make GPs less prone to adhere to erroneous diagnostics results. The findings suggest that, when the AI was correct, the GPs’ ability to correctly diagnose a skin lesion significantly improved after receiving correct AI information, from 73.6% to 86.8% (X2 (1, N = 50) = 21.787, p < 0.001), with significant effects for both the benign (X2 (1, N = 50) = 21, p < 0.001) and malignant cases (X2 (1, N = 50) = 4.654, p = 0.031). However, when the AI provided erroneous information, only 10% of the GPs were able to correctly disagree with the indication of the AI in terms of diagnosis (d-AIW M: 0.12, SD: 0.37), and only 14% of participants were able to correctly decide the management plan despite the AI insights (d-AIW M:0.12, SD: 0.32). The analysis of the difference between groups in terms of individual characteristics suggested that GPs with domain knowledge in dermatology were better at rejecting the wrong insights from AI.

scholarly journals Clinical pathways for primary care: current use, interest and perceived usability

2018 ◽  
Vol 25 (7) ◽  
pp. 901-906 ◽  
Author(s):  
Jennifer M Toy ◽  
Adam Drechsler ◽  
Richard C Waters
Keyword(s):  
Primary Care ◽  
Online Survey ◽  
Clinical Pathways ◽  
Decision Support Tool ◽  
Daily Practice ◽  
Support Tool ◽  
System Usability Scale ◽  
Primary Care Clinicians ◽  
Perceived Usability ◽  
Tool Types

Abstract Objective Translating clinical evidence to daily practice remains a challenge and may improve with clinical pathways. We assessed interest in and usability of clinical pathways by primary care professionals. Methods An online survey was created. Interest in pathways for patient care and learning was assessed at start and finish. Participants completed baseline questions then pathway-associated question sets related to management of 2 chronic diseases. Perceived pathway usability was assessed using the system usability scale. Accuracy and confidence of answers was compared for baseline and pathway-assisted questions. Results Of 115 participants, 17.4% had used clinical pathways, the lowest of decision support tool types surveyed. Accuracy and confidence in answers significantly improved for all pathways. Interest in using pathways daily or weekly was above 75% for the respondents. Conclusion There is low utilization of, but high interest in, clinical pathways by primary care clinicians. Pathways improve accuracy and confidence in answering written clinical questions.

scholarly journals Impact of Artificial Intelligence, With and Without Information, on Pathologists’ Decisions: An Experiment

2021 ◽  
Author(s):  
Julien Meyer ◽  
April Khademi ◽  
Bernard Têtu ◽  
Wencui Han ◽  
Pria Nippak ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Decision Aid ◽  
Online Survey ◽  
Decision Aids ◽  
Survey Study ◽  
Gleason Grade ◽  
Accuracy Rate ◽  
Significant Difference ◽  
The Difference ◽  
The Individual

Abstract Background: Artificial intelligence (AI) is rapidly gaining attention in medicine and in pathology in particular. While much progress has been made in refining the accuracy of algorithms, thereby increasing their potential use, we need to better understand how these algorithms will be used by pathologists, who will remain for the foreseeable future the decision-makers. The objective of this paper is to determine the propensity of pathologists to rely on AI decision aids and to investigate whether providing information on the algorithm impacts this reliance.Methods: To test our hypotheses, we conducted an experiment with within-subjects design using an online survey study. 116 respondent pathologists and pathology students participated in the experiment. Each participant was tasked with assessing the Gleason grade for a series of 12 prostate cancer samples under three conditions: without advice, with advice from an AI decision aid, and with advice from an AI decision aid with information provided on the algorithm, namely the algorithm accuracy rate and the algorithm model. Scores were computed by comparing the respondents’ scores with the “true” score at the individual-question level. A mixed effects logistic regression was used to analyze the difference in scores between the different conditions, controlling for the random effects of participants and images and to assess the interactions with Experience, Gender and beliefs towards AI.Results: Participant responses to the questions with AI decision aids were significantly more accurate than the control condition without aid. However, no significant difference was found when subjects were provided with additional accuracy rate and model information on the AI advice. Moreover, the propensity to rely on AI was found to relate to general beliefs on AI but not with particular assessments of the AI tool offered. Males also performed better in the No-aid condition but not in the AI-aid condition.Conclusions: AI can significantly influence pathologists and the general beliefs in AI could be major predictors of future reliance on AI by pathologists.

scholarly journals Autonomous, Connected Ultrasonic Microsystem Dedicated to Monitoring the Pathophysiology of the Phonic and Respiratory Apparatus

2020 ◽  
Vol 19 ◽  
Keyword(s):  
Artificial Intelligence ◽  
Decision Support ◽  
Respiratory Failure ◽  
Healthcare Professionals ◽  
Decision Support Tool ◽  
Support Tool ◽  
Remote Assessment ◽  
Multidimensional Information ◽  
Respiratory Apparatus

This work tackles a combination of two technological fields: "integrated ultrasonic biosensors" and "connected modules" coupled with “Artificial Intelligence” algorithms to provide healthcare professionals with additional indices offering multidimensional information and a “Decision Support” tool. This device comprises a connected telemedical platform (PC or Smartphone) dedicated to the objective and remote assessment of pathophysiological states resulting from dysphonia of laryngeal origin or respiratory failure of inflammatory origin.

Abstract 219: Health Literacy and Numeracy in Patients Considering a Left Ventricular Assist Device: Findings From the DECIDE-LVAD Trial

2018 ◽  
Vol 11 (suppl_1) ◽  
Author(s):  
David S Raymer ◽  
Larry A Allen ◽  
Daniel D Matlock ◽  
Colleen K McIlvennan ◽  
Jocelyn S Thompson ◽  
...  
Keyword(s):  
Decision Support ◽  
Health Literacy ◽  
Decision Support Tool ◽  
Left Ventricular ◽  
Low Literacy ◽  
Ventricular Assist ◽  
Support Tool ◽  
Low Health Literacy ◽  
Left Ventricular Assist ◽  
The Difference

Introduction: The DECIDE-LVAD Trial demonstrated the benefit of a decision support tool for patients considering destination-therapy left ventricular assist device (DT LVAD) implantation. We hypothesized that patients with low health literacy or numeracy may have benefited most from the intervention. Methods: We used the Rapid Estimate of Adult Literacy in Medicine (REALM-R) and the Subjective Numeracy Scale (SNS) to assess patients’ health literacy and numeracy, respectively. A REALM-R score of six or less out of eight identified patients at risk for poor literacy based on the original measure validation. An SNS score less than four out of six identified patients with poor subjective numeracy based on the mean score of the DECIDE-LVAD cohort. We assessed the effect of the decision support tool on LVAD knowledge and values-treatment concordance—concordance between patients’ stated values and their treatment outcome of LVAD or continued medical therapy—and their interaction with health literacy and numeracy. This interaction was assessed using linear mixed models for LVAD knowledge and the difference in Kendall’s tau correlation coefficient for values-treatment concordance. Results: Of the 248 DECIDE-LVAD patients, 228 with complete literacy and numeracy data were analyzed: 51% (116) had high literacy and numeracy; 18 (8%) had low literacy and high numeracy; 55 (25%) had high literacy and low numeracy; 39 (17%) had low scores for both measures. Average age was 63, 15% were female, 19% were racial/ethnic minorities. Patients with high scores for both measures were older, had more formal education, and higher total household income compared to the other 3 groups. Patients with low literacy and/or numeracy had significantly lower LVAD knowledge scores at baseline. In all groups, LVAD knowledge improved over time. The difference in LVAD knowledge between those with low literacy and high literacy decreased over time (baseline difference 9.4%, p=0.002; 6 month follow-up difference 1.4%, p=0.65). In those with high literacy, the decision support tool intervention increased the LVAD knowledge score by 4.2% relative to the control (p=0.15), while in those with low literacy, the intervention increased the score by 10.6% (p=0.04). For patients with low literacy, values-treatment concordance improved with use of the decision support tool (control vs. intervention tau: 0.234 vs 0.673, p=0.028). We did not observe differences in the effect of the intervention by participant numeracy score. Conclusion: All patient groups in the DECIDE-LVAD cohort of patients considering DT LVAD had improved LVAD knowledge with the use of the decision support tool. We did not observe a differential effect of the intervention by numeracy score. Compared to those with higher health literacy, patients with low health literacy improved their LVAD knowledge and values-treatment concordance after the intervention.

Video Analytics for Railroad Safety Research: An Artificial Intelligence Approach

2018 ◽  
Vol 2672 (10) ◽  
pp. 269-277 ◽  
Author(s):  
Asim Zaman ◽  
Xiang Liu ◽  
Zhipeng Zhang
Keyword(s):  
Artificial Intelligence ◽  
Big Data ◽  
Decision Support Tool ◽  
Video Data ◽  
Near Miss ◽  
Support Tool ◽  
Near Misses ◽  
Railroad Industry ◽  
Safety Research ◽  
Railroad Safety

The volume of video data in the railroad industry has increased significantly in recent years. Surveillance cameras are situated on nearly every part of the railroad system, such as inside the cab, along the track, at grade crossings, and in stations. These camera systems are manually monitored, either live or subsequently reviewed in an archive, which requires an immense amount of human resources. To make the video analysis much less labor-intensive, this paper develops a framework for utilizing artificial intelligence (AI) technologies for the extraction of useful information from these big video datasets. This framework has been implemented based on the video data from one grade crossing in New Jersey. The AI algorithm can automatically detect unsafe trespassing of railroad tracks (called near-miss events in this paper). To date, the AI algorithm has analyzed hours of video data and correctly detected all near-misses. This pilot study indicates the promise of using AI for automated analysis of railroad video big data, thereby supporting data-driven railroad safety research. For practical use, our AI algorithm has been packaged into a computer-aided decision support tool (named AI-Grade) that outputs near-miss video clips based on user-provided raw video data. This paper and its sequent studies aim to provide the railroad industry with next-generation big data analysis methods and tools for quickly and reliably processing large volumes of video data in order to better understand human factors in railroad safety research.

Sign in / Sign up

Export Citation Format

Share Document